Ireland

The performance of deep learning models in NLP and other fields of machine learning has led to a rise in their popularity, and so the need for explanations of these models becomes paramount. Attention has been seen as a solution to increase performance, while providing some explanations. However, a debate has started to cast doubt on the explanatory power of attention in neural networks. Although the debate has created a vast literature thanks to contributions from various areas, the lack of communication is becoming more and more tangible. In this paper, we provide a clear overview of the insights on the debate by critically confronting works from these different areas. This holistic vision can be of great interest for future works in all the communities concerned by this debate. We sum up the main challenges spotted in these areas, and we conclude by discussing the most promising future avenues on attention as an explanation.

ACL 2022

Is Attention Explanation? An Introduction to the Debate

explanation

explainability

attention

neural networks

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

findings / work in progress

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). 

Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no significant update since the past decade. Word and sentence similarity tasks have become the de facto evaluation method. It leads models to overfit to such evaluations, negatively impacting embedding models' development. This paper first points out the problems using semantic similarity as the gold standard for word and sentence embedding evaluations. Further, we propose a new intrinsic evaluation method called EvalRank, which shows a much stronger correlation with downstream tasks. Extensive experiments are conducted based on 60+ models and popular datasets to certify our judgments. Finally, the practical evaluation toolkit is released for future benchmarking purposes.

Just Rank: Rethinking Evaluation with Word and Sentence Similarities

In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of label-semantics during pre-training has not been extensively explored. We therefore propose Label Semantic Aware Pre-training (LSAP) to improve the generalization and data efficiency of text classification systems. LSAP incorporates label semantics into pre-trained generative models (T5 in our case) by performing secondary pre-training on labeled sentences from a variety of domains. As domain-general pre-training requires large amounts of data, we develop a filtering and labeling pipeline to automatically create sentence-label pairs from unlabeled text. We perform experiments on intent (ATIS, Snips, TOPv2) and topic classification (AG News, Yahoo! Answers). LSAP obtains significant accuracy improvements over state-of-the-art models for few-shot text classification while maintaining performance comparable to state of the art in high-resource settings.

Label Semantic Aware Pre-training for Few-shot Text Classification

Laws and their interpretations, legal arguments and agreements are typically expressed in writing, leading to the production of vast corpora of legal text. Their analysis, which is at the center of legal practice, becomes increasingly elaborate as these collections grow in size. Natural language understanding (NLU) technologies can be a valuable tool to support legal practitioners in these endeavors. Their usefulness, however, largely depends on whether current state-of-the-art models can generalize across various tasks in the legal domain. To answer this currently open question, we introduce the Legal General Language Understanding Evaluation (LexGLUE) benchmark, a collection of datasets for evaluating model performance across a diverse set of legal NLU tasks in a standardized way. We also provide an evaluation and analysis of several generic and legal-oriented models demonstrating that the latter consistently offer performance improvements across multiple tasks.

LexGLUE: A Benchmark Dataset for Legal Language Understanding in English

Classifiers in natural language processing (NLP) often have a large number of output
classes. For example, neural language models (LMs) and machine translation (MT) models both predict tokens from a vocabulary of thousands. The Softmax output layer of these models typically receives as input a dense feature representation, which has much lower dimensionality than the output. In theory, the result is some words may be impossible to be predicted via argmax, irrespective of input features, and empirically, there is evidence this happens in small language models (Demeter et al., 2020). In this paper we ask whether it can happen in practical large language models and translation models. To do so, we develop algorithms to detect such unargmaxable tokens in public models. We find that 13 out of 150 models do indeed have such tokens; however, they are very infrequent and unlikely to impact model quality. We release our algorithms and code so that others can test their models.

Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice

Social media platforms are deploying machine learning based offensive language classification systems to combat hateful, racist, and other forms of offensive speech at scale. However, despite their real-world deployment, we do not yet comprehensively understand the extent to which offensive language classifiers are robust against adversarial attacks. Prior work in this space is limited to studying robustness of offensive language classifiers against primitive attacks such as misspellings and extraneous spaces. To address this gap, we systematically analyze the robustness of state-of-the-art offensive language classifiers against more crafty adversarial attacks that leverage greedy- and attention-based word selection and context-aware embeddings for word replacement. Our results on multiple datasets show that these crafty adversarial attacks can degrade the accuracy of offensive language classifiers by more than 50% while also being able to preserve the readability and meaning of the modified text.

On the Robustness of Offensive Language Classifiers

Knowledge probing is crucial for understanding the knowledge transfer mechanism behind the pre-trained language models (PLMs). Despite the growing progress of probing knowledge for PLMs in the general domain, specialised areas such as biomedical domain are vastly under-explored. To catalyse the research in this direction, we release a well-curated biomedical knowledge probing benchmark, MedLAMA, which is constructed based on the Unified Medical Language System (UMLS) Metathesaurus. We test a wide spectrum of state-of-the-art PLMs and probing approaches on our benchmark, reaching at most 3% of acc@10. While highlighting various sources of domain-specific challenges that amount to this underwhelming performance, we illustrate that the underlying PLMs have a higher potential for probing tasks. To achieve this, we propose Contrastive-Probe, a novel self-supervised contrastive probing approach, that adjusts the underlying PLMs without using any probing data. While Contrastive-Probe pushes the acc@10 to 28%, the performance gap still remains notable. Our human expert evaluation suggests that the probing performance of our Contrastive-Probe is still under-estimated as UMLS still does not include the full spectrum of factual knowledge. We hope MedLAMA and Contrastive-Probe facilitate further developments of more suited probing techniques for this domain.

Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models

Understanding tables is an important aspect of natural language understanding. Existing models for table understanding require linearization of the table structure, where row or column order is encoded as an unwanted bias. Such spurious biases make the model vulnerable to row and column order perturbations. Additionally, prior work has not thoroughly modeled the table structures or table-text alignments, hindering the table-text understanding ability. In this work, we propose a robust and structurally aware table-text encoding architecture TableFormer, where tabular structural biases are incorporated completely through learnable attention biases. TableFormer is (1) strictly invariant to row and column orders, and, (2) could understand tables better due to its tabular inductive biases. Our evaluations showed that TableFormer outperforms strong baselines in all settings on SQA, WTQ and TabFact table reasoning datasets, and achieves state-of-the-art performance on SQA, especially when facing answer-invariant row and column order perturbations (6% improvement over the best baseline), because previous SOTA models' performance drops by 4% - 6% when facing such perturbations while TableFormer is not affected.

TableFormer: Robust Transformer Modeling for Table-Text Encoding

The learning trajectories of linguistic phenomena in humans provide insight into linguistic representation, beyond what can be gleaned from inspecting the behavior of an adult speaker. To apply a similar approach to analyze neural language models (NLM), it is first necessary to establish that different models are similar enough in the generalizations they make. 
In this paper, we show that NLMs with different initialization, architecture, and training data acquire linguistic phenomena in a similar order, despite their different end performance. These findings suggest that there is some mutual inductive bias that underlies these models' learning of linguistic phenomena. Taking inspiration from psycholinguistics, we argue that studying this inductive bias is an opportunity to study the linguistic representation implicit in NLMs.

The Grammar-Learning Trajectories of Neural Language Models

Interpretability of semantic textual similarity (STS) is important for understanding how the similarity is made. In this presentation, we briefly introduce three useful outcomes described in the paper: an analytic method for STS, an approach of computing STS, and the training framework for STS. We show the effectiveness of these outcomes with various experimental settings.

Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning

We present a complete pipeline to extract characters in a novel and link them to their direct-speech utterances. Our model is divided into three independent components: extracting direct-speech, compiling a list of characters, and attributing those characters to their utterances. Although we find that existing systems can perform the first two tasks accurately, attributing characters to direct speech is a challenging problem due to the narrator's lack of explicit character mentions, and the frequent use of nominal and pronominal coreference when such explicit mentions are made. We adapt the progress made on Dialogue State Tracking to tackle a new problem: attributing speakers to dialogues. This is the first application of deep learning to speaker attribution, and it shows that is possible to overcome the need for the hand-crafted features and rules used in the past. Our full pipeline improves the performance of state-of-the-art models by a relative 50% in F1-score.

Downloads

Next from ACL 2022

Just Rank: Rethinking Evaluation with Word and Sentence Similarities

Similar lecture

Multiple LLM Agents Debate for Equitable Cultural Alignment